Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2909 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.8085. Min Act: -0.1700
Data Index: 4928436 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.7772. Min Act: -0.1700
Data Index: 8215596 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.7772. Min Act: -0.1700
Data Index: 759026 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.6835. Min Act: -0.1700
Data Index: 1610253 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.6522. Min Act: -0.1700
Data Index: 5318108 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.6522. Min Act: -0.1700
Data Index: 511493 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.6835. Min Act: -0.1700
Data Index: 6419779 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.6522. Min Act: -0.1700
Data Index: 7565415 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.6210. Min Act: -0.1700
Data Index: 4781862 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.6210. Min Act: -0.1700
Data Index: 5088022 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.5897. Min Act: -0.1700
Data Index: 1326714 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.5585. Min Act: -0.1700
Data Index: 4824177 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.5272. Min Act: -0.1700
Data Index: 3669210 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.4960. Min Act: -0.1700
Data Index: 835243 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.5272. Min Act: -0.1700
Data Index: 5054545 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.4960. Min Act: -0.1700
Data Index: 8131654 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.4960. Min Act: -0.1700
Data Index: 1815163 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.4647. Min Act: -0.1700
Data Index: 7342346 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.4647. Min Act: -0.1700
Data Index: 5088021 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.4335. Min Act: -0.1700
Data Index: 7994188 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19